.png){kind=icon}
返回
Deep API Sequence Generation via Golden Solution Samples and API Seeds
.png){kind=icon}
PRE
AI
DOI：10.1145/3695995.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Automatic API recommendation can accelerate developers' programming and has been studied for years. There are two orthogonal lines of approaches for this task, i.e., information retrieval-based (IR-based) approaches and sequence to sequence (seq2seq) model-based approaches. Although these approaches were reported to have remarkable performance, our observation finds two major drawbacks, i.e., IR-based approaches lack the consideration of relations among the recommended APIs, and seq2seq models do not model the API's semantic meaning. To alleviate the above two problems, we propose APIGens, which is a retrieval-enhanced large language model (LLM)-based API recommendation approach to recommend an API sequence for a natural language query. The approach first retrieves similar programming questions in history based on the input natural language query, and then scores the results based on API documents via a scorer model. Finally, these results are used as samples for few-shot learning of LLM. To reduce the risk of encountering local optima, we also extract API seeds from the retrieved results to increase the search scope during the LLM generation process. The results show that our approach can achieve 48.41% ROUGE@10 on API sequence recommendation and the 82.61% MAP on API set recommendation, largely outperforming the state-of-the-art baselines.
Keyword:
API recommendation
deep learning
information retrieval
sequence generation
large language model
期刊
A
IF:
6.2
论文数:
1.2K
被引数:
3.4K
机构
引用论文
Sodium channel kinetic changes that produce Brugada syndrome or progressive cardiac conduction system disease产生Brugada综合征或进行性心脏传导系统疾病的钠通道动力学变化
.png){kind=icon}
PREAI
分享收藏
分享收藏
查看更多内容